Keras 2 API documentation / Keras Applications / ConvNeXt Tiny, Small, Base, Large, XLarge

ConvNeXt Tiny, Small, Base, Large, XLarge

[source]

ConvNeXtTiny function

tf_keras.applications.ConvNeXtTiny(
    model_name="convnext_tiny",
    include_top=True,
    include_preprocessing=True,
    weights="imagenet",
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation="softmax",
)

Instantiates the ConvNeXtTiny architecture.

References

For image classification use cases, see this page for detailed examples. For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

The base, large, and xlarge models were first pre-trained on the ImageNet-21k dataset and then fine-tuned on the ImageNet-1k dataset. The pre-trained parameters of the models were assembled from the official repository. To get a sense of how these parameters were converted to TF-Keras compatible parameters, please refer to this repository.

Note: Each TF-Keras Application expects a specific kind of input preprocessing. For ConvNeXt, preprocessing is included in the model using a Normalization layer. ConvNeXt models expect their inputs to be float or uint8 tensors of pixels with values in the [0-255] range.

When calling the summary() method after instantiating a ConvNeXt model, prefer setting the expand_nested argument summary() to True to better investigate the instantiated model.

Arguments

  • include_top: Whether to include the fully-connected layer at the top of the network. Defaults to True.
  • weights: One of None (random initialization), "imagenet" (pre-training on ImageNet-1k), or the path to the weights file to be loaded. Defaults to "imagenet".
  • input_tensor: Optional TF-Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
  • pooling: Optional pooling mode for feature extraction when include_top is False.
    • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
    • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied. Defaults to None.
  • classes: Optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified. 1000 is how many ImageNet classes there are. Defaults to 1000.
  • classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. When loading pretrained weights, classifier_activation can only be None or "softmax". Defaults to "softmax".

Returns

A keras.Model instance.


[source]

ConvNeXtSmall function

tf_keras.applications.ConvNeXtSmall(
    model_name="convnext_small",
    include_top=True,
    include_preprocessing=True,
    weights="imagenet",
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation="softmax",
)

Instantiates the ConvNeXtSmall architecture.

References

For image classification use cases, see this page for detailed examples. For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

The base, large, and xlarge models were first pre-trained on the ImageNet-21k dataset and then fine-tuned on the ImageNet-1k dataset. The pre-trained parameters of the models were assembled from the official repository. To get a sense of how these parameters were converted to TF-Keras compatible parameters, please refer to this repository.

Note: Each TF-Keras Application expects a specific kind of input preprocessing. For ConvNeXt, preprocessing is included in the model using a Normalization layer. ConvNeXt models expect their inputs to be float or uint8 tensors of pixels with values in the [0-255] range.

When calling the summary() method after instantiating a ConvNeXt model, prefer setting the expand_nested argument summary() to True to better investigate the instantiated model.

Arguments

  • include_top: Whether to include the fully-connected layer at the top of the network. Defaults to True.
  • weights: One of None (random initialization), "imagenet" (pre-training on ImageNet-1k), or the path to the weights file to be loaded. Defaults to "imagenet".
  • input_tensor: Optional TF-Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
  • pooling: Optional pooling mode for feature extraction when include_top is False.
    • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
    • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied. Defaults to None.
  • classes: Optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified. 1000 is how many ImageNet classes there are. Defaults to 1000.
  • classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. When loading pretrained weights, classifier_activation can only be None or "softmax". Defaults to "softmax".

Returns

A keras.Model instance.


[source]

ConvNeXtBase function

tf_keras.applications.ConvNeXtBase(
    model_name="convnext_base",
    include_top=True,
    include_preprocessing=True,
    weights="imagenet",
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation="softmax",
)

Instantiates the ConvNeXtBase architecture.

References

For image classification use cases, see this page for detailed examples. For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

The base, large, and xlarge models were first pre-trained on the ImageNet-21k dataset and then fine-tuned on the ImageNet-1k dataset. The pre-trained parameters of the models were assembled from the official repository. To get a sense of how these parameters were converted to TF-Keras compatible parameters, please refer to this repository.

Note: Each TF-Keras Application expects a specific kind of input preprocessing. For ConvNeXt, preprocessing is included in the model using a Normalization layer. ConvNeXt models expect their inputs to be float or uint8 tensors of pixels with values in the [0-255] range.

When calling the summary() method after instantiating a ConvNeXt model, prefer setting the expand_nested argument summary() to True to better investigate the instantiated model.

Arguments

  • include_top: Whether to include the fully-connected layer at the top of the network. Defaults to True.
  • weights: One of None (random initialization), "imagenet" (pre-training on ImageNet-1k), or the path to the weights file to be loaded. Defaults to "imagenet".
  • input_tensor: Optional TF-Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
  • pooling: Optional pooling mode for feature extraction when include_top is False.
    • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
    • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied. Defaults to None.
  • classes: Optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified. 1000 is how many ImageNet classes there are. Defaults to 1000.
  • classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. When loading pretrained weights, classifier_activation can only be None or "softmax". Defaults to "softmax".

Returns

A keras.Model instance.


[source]

ConvNeXtLarge function

tf_keras.applications.ConvNeXtLarge(
    model_name="convnext_large",
    include_top=True,
    include_preprocessing=True,
    weights="imagenet",
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation="softmax",
)

Instantiates the ConvNeXtLarge architecture.

References

For image classification use cases, see this page for detailed examples. For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

The base, large, and xlarge models were first pre-trained on the ImageNet-21k dataset and then fine-tuned on the ImageNet-1k dataset. The pre-trained parameters of the models were assembled from the official repository. To get a sense of how these parameters were converted to TF-Keras compatible parameters, please refer to this repository.

Note: Each TF-Keras Application expects a specific kind of input preprocessing. For ConvNeXt, preprocessing is included in the model using a Normalization layer. ConvNeXt models expect their inputs to be float or uint8 tensors of pixels with values in the [0-255] range.

When calling the summary() method after instantiating a ConvNeXt model, prefer setting the expand_nested argument summary() to True to better investigate the instantiated model.

Arguments

  • include_top: Whether to include the fully-connected layer at the top of the network. Defaults to True.
  • weights: One of None (random initialization), "imagenet" (pre-training on ImageNet-1k), or the path to the weights file to be loaded. Defaults to "imagenet".
  • input_tensor: Optional TF-Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
  • pooling: Optional pooling mode for feature extraction when include_top is False.
    • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
    • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied. Defaults to None.
  • classes: Optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified. 1000 is how many ImageNet classes there are. Defaults to 1000.
  • classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. When loading pretrained weights, classifier_activation can only be None or "softmax". Defaults to "softmax".

Returns

A keras.Model instance.


[source]

ConvNeXtXLarge function

tf_keras.applications.ConvNeXtXLarge(
    model_name="convnext_xlarge",
    include_top=True,
    include_preprocessing=True,
    weights="imagenet",
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation="softmax",
)

Instantiates the ConvNeXtXLarge architecture.

References

For image classification use cases, see this page for detailed examples. For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

The base, large, and xlarge models were first pre-trained on the ImageNet-21k dataset and then fine-tuned on the ImageNet-1k dataset. The pre-trained parameters of the models were assembled from the official repository. To get a sense of how these parameters were converted to TF-Keras compatible parameters, please refer to this repository.

Note: Each TF-Keras Application expects a specific kind of input preprocessing. For ConvNeXt, preprocessing is included in the model using a Normalization layer. ConvNeXt models expect their inputs to be float or uint8 tensors of pixels with values in the [0-255] range.

When calling the summary() method after instantiating a ConvNeXt model, prefer setting the expand_nested argument summary() to True to better investigate the instantiated model.

Arguments

  • include_top: Whether to include the fully-connected layer at the top of the network. Defaults to True.
  • weights: One of None (random initialization), "imagenet" (pre-training on ImageNet-1k), or the path to the weights file to be loaded. Defaults to "imagenet".
  • input_tensor: Optional TF-Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
  • pooling: Optional pooling mode for feature extraction when include_top is False.
    • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
    • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied. Defaults to None.
  • classes: Optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified. 1000 is how many ImageNet classes there are. Defaults to 1000.
  • classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. When loading pretrained weights, classifier_activation can only be None or "softmax". Defaults to "softmax".

Returns

A keras.Model instance.